Multi-sensor Information Fusion and Control of Robot Spot Welding

Spot welding quality is always one of questions under study,to which many welding scholars in the world devote themselves.It has not been solved satisfactorily at present.The complex nature of spot welding process, undeterminedness of grown nugget and singleness of control method decide that stabilizing quality is a much difficult task.The limitations of describing how the nugget growing up in view of single-sensor information source is analyzed in the paper.An idea of using multi-sensor information fusion for spot welding quality control is presented for the first time.The information fusion model for weld spot nugget is established through parameter selecting and characteristic information extracting. Heat and time adjustment of spot welding process are made through the best fusion arithmetic adapting combined,average and decision-making methods.The spot welding experiments indicate that the new quality control method can better compensate various factors influence in the welding process and assure the spot welding quality stabilization.